Key result
An ordinary least squares regression model using anthropometric and submaximal exercise data predicted VO2max with an R2 of 0.83, and a support vector machine classified fitness levels with 75% accuracy.
Why the study?
Maximal oxygen consumption reflects aerobic capacity and is crucial for assessing cardiorespiratory fitness, but methods are needed to classify and predict population-based cardiorespiratory fitness from submaximal exercise parameters.
Can machine learning models accurately predict and classify cardiorespiratory fitness (VO2max) using anthropometric parameters and submaximal exercise test data in healthy adults?
Comparison
VO 2 max predicted via regression vs measured VO 2 max from a submaximal cycle test
Authors
Loading...
May support scalable VO2max estimation in healthy adults; hypothesis-generating pending prospective validation.
Cross-Sectional (n=517)
No
Can machine learning models accurately predict and classify cardiorespiratory fitness (VO2max) using anthropometric parameters and submaximal exercise test data in healthy adults?
Effect estimate: R2 0.83
Machine learning models using basic anthropometric and submaximal exercise data can accurately predict VO2max, providing a scalable method for population-level cardiorespiratory fitness assessment.
Xiang et al. (2022) conducted a cross-sectional in Healthy (cardiorespiratory fitness assessment) (n=517). Anthropometric and submaximal exercise test predictors was evaluated on Prediction accuracy of VO2max (Coefficient of determination, R2) (R2 0.83). An ordinary least squares regression model using anthropometric and submaximal exercise data predicted VO2max with an R2 of 0.83, and a support vector machine classified fitness levels with 75% accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: